google-ads-measurementlisted

# Google Ads — Measurement (tracking gate) Prove conversion tracking is correct and trustworthy, or block `plan`/`builder-*` until it is. Reuse the live MCP detection from `setup`. **Never raise an alarm from the action list alone.** ## STEP 0 — Load context **If `account-context.yaml` is missing, run `setup` first — don't validate tracking on an unconfigured account.** Read `account-context.yaml`: `google_ads.customer_id`, `conversion_actions`, `measurement.*`, `data_source` (for value sanity), `business.model/vertical` (lead vs purchase expectations). Output goes to the working directory; update the context's `conversion_actions` + `measurement.*` as you verify them. ## Model dispatch (run cheap, decide expensive) — see `${CLAUDE_PLUGIN_ROOT}/references/model-tier-dispatch.md` - **Scout (`haiku`)** — STEP 0 context read; the conversion-action list pull. - **Routine (`sonnet`)** — STEP 1 per-campaign conversion segmentation (`segments.conversion_action_name`), STEP 3 Ads/GA4/store value pulls. Dispatch as `general-purpose` sub-agents; **return raw, don't conclude**. - **Judge (main session)** — the WHOLE-picture verdict, every is-it-a-problem call, the double-count judgment, the PASS/WARN/FAIL that gates plan/builder. **Never let a cheap tier raise the alarm** — that holistic judgment is the entire point of this skill. ## STEP 1 — Build the WHOLE picture before concluding (mandatory) A conversion list read in isolation lies. The same flag is fine or fatal depending on co